© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6994
    Prev
    Next
    INDEX
    Explanations

    code or functions related to programming, specifically in VBA

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets: loops, variable assignments, and queries

    np_acts-logits-general · gemini-2.0-flash

    code and math expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.84
    __':
    -0.81
     pinulongan
    -0.75
    ResumeLayout
    -0.71
    __":
    -0.70
     שוליים
    -0.70
    /**
    -0.65
    '}>
    -0.64
    Посилання
    -0.64
    DeclareMath
    -0.64
    POSITIVE LOGITS
     scolas
    0.53
    ritsar
    0.49
     legais
    0.47
    西兰
    0.47
    avut
    0.46
     Zeeland
    0.46
     Bachchan
    0.45
     studenti
    0.45
     tableta
    0.44
    ombic
    0.44
    Activations Density 0.618%

    No Known Activations